© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25851
    Prev
    Next
    INDEX
    Explanations

    favorite fests and bands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <strong>
    -1.06
     N
    -1.05
    蔡
    -1.01
    𓂂
    -1.01
     K
    -1.01
     J
    -0.99
    styrelsen
    -0.98
     Daniel
    -0.97
     Y
    -0.96
    <em>
    -0.96
    POSITIVE LOGITS
     sés
    1.23
     mémor
    1.20
     phénom
    1.15
     televiz
    1.15
     sevilla
    1.14
    ホント
    1.13
     fuis
    1.13
     corrom
    1.12
     suman
    1.12
    خيص
    1.10
    Activations Density 0.106%

    No Known Activations